Feature extraction from faces using deformable templates
Alan Yuille, D.S. Cohen, Peter W. Hallinan · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2003
A method for detecting and describing the features of faces using deformable templates is described. The feature of interest, an eye for example, is described by a parameterized template. An energy function is defined which links edges, peaks, and valleys in the image intensity to corresponding properties of the template. The template then interacts dynamically with the image, by altering its parameter values to minimize the energy function, thereby deforming itself to find the best fit. The final parameter values can be used as descriptors for the features. This method is demonstrated by showing deformable templates detecting eyes and mouths in real images.>
Cited by 708 works. doi:10.1109/cvpr.1989.37836
Authors
References
- Snakes: Active contour models
- Monte Carlo Methods
- Computer vision
- Image analysis and mathematical morphology
- The Representation and Matching of Pictorial Structures
- Image Analysis and Mathematical Morphology.
- An analogue approach to the travelling salesman problem using an elastic net method
- Elastic Matching of Line Drawings
- Symmetry-seeking models and 3D object reconstruction
- A dynamic model for image registration